© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38484
    Prev
    Next
    INDEX
    Explanations

    known about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffekt
    -1.64
    Faktor
    -1.37
    drei
    -1.25
     rutina
    -1.22
    Mitar
    -1.20
     problém
    -1.18
    einer
    -1.17
    Dokument
    -1.17
    Charakter
    -1.17
    Meine
    -1.16
    POSITIVE LOGITS
     about
    4.25
     of
    1.66
     tentang
    1.61
     from
    1.56
     regarding
    1.55
     kuhusu
    1.42
    about
    1.40
     hakkında
    1.34
     mengenai
    1.34
     siitä
    1.32
    Activations Density 0.050%

    No Known Activations